© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14313
    Prev
    Next
    INDEX
    Explanations

    Green Woman selection criteria firearm access

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on the very first word of a sentence, detecting sentence-initial tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ॓
    0.91
    ﺮ
    0.88
    minsize
    0.86
    く
    0.84
    чний
    0.82
    цен
    0.81
    ਾਮ
    0.79
     والح
    0.79
    学科
    0.79
    蛭
    0.76
    POSITIVE LOGITS
    ↵
    0.82
    yc
    0.77
    nt
    0.75
    na
    0.73
     Yr
    0.70
    ynt
    0.69
    dat
    0.68
     Aufl
    0.65
     yr
    0.64
    Lc
    0.64
    Activations Density 0.000%

    No Known Activations